Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 787 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 942686 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2766. Min Act: -0.0000

Data Index: 515407 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1232937 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1230919 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2471. Min Act: -0.0000

Data Index: 933325 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1031902 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1023311 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1809464 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2379. Min Act: -0.0000

Data Index: 391229 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2458. Min Act: -0.0000

Data Index: 548466 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2191. Min Act: -0.0000

Data Index: 965985 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2394. Min Act: -0.0000

Data Index: 976186 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2388. Min Act: -0.0000

Data Index: 385411 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2031. Min Act: -0.0000

Data Index: 422180 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1956368 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1914364 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1209706 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1619236 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2278. Min Act: -0.0000

Data Index: 616435 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1574547 (The Pile)

Max Activating Token Index: 30